© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26212
    Prev
    Next
    INDEX
    Explanations

    location or proximity search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __/
    -0.08
    Qi
    -0.08
     Yankee
    -0.08
     Comparable
    -0.08
     staples
    -0.08
     Ryder
    -0.08
    ±
    -0.08
    odel
    -0.08
     consort
    -0.08
    ylan
    -0.08
    POSITIVE LOGITS
     tutors
    0.13
     nearby
    0.12
     near
    0.12
     proximity
    0.11
     tutoring
    0.11
     Nearby
    0.11
     Harden
    0.11
     prox
    0.11
    -distance
    0.11
     tutor
    0.11
    Activations Density 0.033%

    No Known Activations